Using the discrepancy between an image and its mask-conditioned Stable Diffusion reconstruction, G4Seg refines coarse segmentation masks by aligning pixels in CLIP feature space and mixing foreground probabilities.
Attrseg: open-vocabulary semantic segmentation via attribute decomposition-aggregation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models
Using the discrepancy between an image and its mask-conditioned Stable Diffusion reconstruction, G4Seg refines coarse segmentation masks by aligning pixels in CLIP feature space and mixing foreground probabilities.